INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     --------↵
    -0.07
    Thai
    -0.07
    .he
    -0.06
    .im
    -0.06
     scoreboard
    -0.06
     fh
    -0.06
    themes
    -0.06
    .dr
    -0.06
    SCORE
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
    apat
    0.09
    jan
    0.07
    Aqu
    0.07
    ArrayType
    0.06
    CGPoint
    0.06
    0.06
     Ban
    0.06
     обязан
    0.06
    dad
    0.06
    APIView
    0.06
    Act Density 0.000%

    No Known Activations